MIMO-Speech: End-To-End Multi-Channel Multi-Speaker Speech Recognition

Xuankai Chang, Wangyou Zhang, Yanmin Qian*, Jonathan Le Roux, Shinji Watanabe

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

71 Citations (Scopus)

Abstract

Recently, the end-To-end approach has proven its efficacy in monaural multi-speaker speech recognition. However, high word error rates (WERs) still prevent these systems from being used in practical applications. On the other hand, the spatial information in multi-channel signals has proven helpful in far-field speech recognition tasks. In this work, we propose a novel neural sequence-To-sequence (seq2seq) architecture, MIMO-Speech, which extends the original seq2seq to deal with multi-channel input and multi-channel output so that it can fully model multi-channel multi-speaker speech separation and recognition. MIMO-Speech is a fully neural end-To-end framework, which is optimized only via an ASR criterion. It is comprised of: 1) a monaural masking network, 2) a multi-source neural beamformer, and 3) a multi-output speech recognition model. With this processing, the input overlapped speech is directly mapped to text sequences. We further adopted a curriculum learning strategy, making the best use of the training set to improve the performance. The experiments on the spatialized wsj1-2mix corpus show that our model can achieve more than 60% WER reduction compared to the single-channel system with high quality enhanced signals (SI-SDR = 23.1 dB) obtained by the above separation function.

Original languageEnglish
Title of host publication2019 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages237-244
Number of pages8
ISBN (Electronic)9781728103068
DOIs
Publication statusPublished - 2019 Dec
Externally publishedYes
Event2019 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019 - Singapore, Singapore
Duration: 2019 Dec 152019 Dec 18

Publication series

Name2019 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019 - Proceedings

Conference

Conference2019 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019
Country/TerritorySingapore
CitySingapore
Period19/12/1519/12/18

Keywords

  • Overlapped speech recognition
  • curriculum learning
  • end-To-end
  • neural beamforming
  • speech separation

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing
  • Linguistics and Language
  • Communication

Fingerprint

Dive into the research topics of 'MIMO-Speech: End-To-End Multi-Channel Multi-Speaker Speech Recognition'. Together they form a unique fingerprint.

Cite this